Edge-Preserved Low-Rank Representation via Multi-Level Knowledge Incorporation for Remote Sensing Image Denoising

Round 1

Reviewer 1 Report

Overall the topic is interesting and important, and the paper is well organized with good results provided. However, there still exist a number of issues that need to be addressed carefully.

1. The experiment is not enough. More experiments should be implemented, such as more state-of-the-art algorithms, more quantitative evaluation indicators. The experimental results were statistically analyzed.

2. There is a lack of analysis of the most cutting-edge literature, and the publication time of references is basically before 2019.

3. The author should evaluate the complexity of the proposed method to establish its superiority over other methods.

4. For the HYDICE Urban dataset, it can be seen from Figure 7 that the filtering results of the proposed algorithm are not superior to the filtering results of the TDL and ITSReg algorithms in terms of noise removal or structure preservation. 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Edge Preserved Low-Rank Representation via Multi-Level Knowledge Incorporation for Remote Sensing Image Denoising:

·        Add some of the most important quantitative results to the Abstract.

·        In the last paragraph of the Introduction, the authors should mention the weak point of former works (identification of the gaps) and describe the novelties of the current investigation to justify that the paper deserves to be published in this journal.

·        “However, it is worth noting that EPLRR-RSID achieves a most smooth vertical mean profile, revealing that our method has the ability to achieve the best denoising performance in HYDICE Urban experiment.”. Explain.

·        Discuss more the parameter sensitivity study in terms of MSSIM.

·        Focus on the advantages/disadvantages of the proposed method concerning the obtained results.

·        At the end of the manuscript, explain the implications and future works considering the outputs of the current study.

 

·        The quality of the language needs to be improved for grammatical style and word use.

The quality of the language needs to be improved for grammatical style and word use.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors addressed all my concerns from the previous round of review. However，if a proper denoising tool can be developed or the source code can be shared, this paper will be much more interesting.

Author Response

Thanks for your valuable suggestion. We are committed to developing a denoising toolbox for remote sensing images, which is based on low-rank model. Specifically, we try to develop the toolbox on both shallow learning and deep learning, and this paper is only part of the toolbox. Till now, the deep learning method is still in progress. Once we finish developing the whole toolbox, we will share the complete source code on github. 

Reviewer 2 Report

I appreciate the authors addressing the comments. The manuscript can be accepted in its current form. Congrats!

I appreciate the authors addressing the comments. The manuscript can be accepted in its current form. Congrats!

Author Response

Thanks for your valuable suggestions before, which have significantly raised the quality of the manuscript and have enabled us to improve the manuscript.